「设计创意」Claude 技能排行榜第 5 页

RunComfy视频编辑：可将现有视频片段进行风格重塑、背景更换、服装更换、动作迁移、颜色分级等操作。

Automate YouTube video editing: download videos, transcribe with Whisper, analyze content using GPT-4, and create Korean SEO-optimized metadata plus consiste...

Generate detailed AI notes including document, outline, and image-text formats from a user-provided video URL using Baidu's video AI notes tool.

插画图片生成技能，支持多种手绘风格。适合流程图、功能说明、PPT配图、教程配图、知识图和手绘信息图等场景。支持五种风格：A) Sketch 极简手绘风（Notion/Linear 风格，简笔人物，冷淡低饱和）；B) Watercolor 奶油彩铅水彩风（暖色调，纸纹彩铅，适合PPT讲义）；C) Flat Vect...

Image-to-video generation on RunComfy. This image-to-video skill turns any still image into a short video clip via the RunComfy Model API. The image-to-video...

Transcribe audio to text using ElevenLabs Scribe. Supports batch transcription, realtime streaming from URLs, microphone input, and local files.

Nano Banana Pro with auto model fallback — generate/edit images via Gemini Image API. Run via: uv run {baseDir}/scripts/generate_image.py --prompt 'desc' --filename 'out.png' [--resolution 1K|2K|4K] [-i input.png]. Supports text-to-image + image-to-image (up to 14); 1K/2K/4K. Fallback chain: gemini-2.5-flash-image → gemini-2.0-flash-exp. MUST use uv run, not python3.

Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine...

Real time video translation / dubbing skill. Translate user-provided video (file or URL) and return preview_url. 适用于视频直译、视频翻译、视频配音、字幕翻译出片。

抖音视频下载工具 - 解析抖音链接，下载视频并发送

Connects to a ComfyUI server to generate images from prompts, auto-detects URLs, translates Chinese prompts, and supports REST and WebSocket APIs.

在 RunComfy 上运行 runcomfy CLI。runcomfy 是一个二进制文件、一次认证、拥有数百个 RunComfy 模型端点——可进行图像生成、图像编辑等功能。

飞书发送文件技能。用于通过飞书向用户发送普通文件附件（HTML、ZIP、PDF、代码文件等）以及处理“本地图片路径被发成路径文本”的可靠补救场景。普通文件必须先上传获取 `file_key` 再发送；当本地图片用 `message`/`media` 发送后在飞书里只显示 `/root/...png` 路径而不显示...

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

AI video generation on RunComfy. This RunComfy video generation skill is a smart router across the RunComfy video-model catalog — HappyHorse 1.0 (Arena #1, n...

{ "translation": "从零构建独特设计系统的完整流程。统筹美学文档、Token 架构、组件与动效。适用于新建或重构设计系统。触发词：创建设计系统、设计 Token、系统搭建、视觉识别、主题化。" }

Text-to-Speech and Speech-to-Text using ElevenLabs AI. Use when the user wants to convert text to speech, transcribe voice messages, or work with voice in multiple languages. Supports high-quality AI voices and accurate transcription.

Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image inpu...

You are a professional media writing expert with extensive experience in creating engaging and impactful content across multiple formats. Creating attention-...

在 RunComfy 上实现 AI 图像生成。该技能是 RunComfy 图像模型目录（包含 FLUX 2（Klein 9B/4B、Pro、D...））的智能路由。

提供剪映官网公开的模板分类、编辑功能、导出规格、版权说明及套餐权益等信息整理和说明服务。

Use when performing video/audio processing tasks including transcoding, filtering, streaming, metadata manipulation, or complex filtergraph operations with FFmpeg.

AI agent content creation and monetization across platforms

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

CAD参考工具

AI image generator skill (image, image generation). Multi-model image generator for Yollomi to generate AI images via one unified API endpoint. Requires YOLL...

Control Apple Music on macOS via the `clawtunes` CLI (play songs/albums/playlists, control playback, volume, shuffle, repeat, search, catalog lookup, AirPlay...

使用火山引擎豆包 Seedream 5.0 生成或编辑图片。支持文生图、单图/多图生图、组图、联网搜索。

将产品需求文档(PRD)转换为完整的设计需求文档,包含信息架构、交互流程、页面布局、视觉规范等内容,并自动生成交互流程图。适用于产品设计、交互设计、UI设计等场景。当用户提供PRD文档并需要设计需求文档时触发此技能。

专业UI生成与现有界面优化技能。当用户请求生成UI界面、设计页面、优化现有界面、创建组件库、设计系统、App界面、Web界面、Dashboard、Landing Page、或任何涉及视觉交互设计时必须触发此技能。参考Google Material Design、Apple HIG、以及Pinterest级别审美标准，输出大气简约、高级美学的UI代码。即使用户只是说"帮我做个界面"、"优化一下UI"、"设计一个页面"也必须触发。

Pure Aliyun ASR skill for voice message transcription, supports multiple channels including Feishu

Clip and download specific time ranges or full YouTube videos in various qualities, including audio-only MP3 extraction, using precise timestamps.

使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。

美图AI全能影像技能库，一站式图像与视频创意解决方案。核心功能涵盖：AI智能海报设计、发丝级精准抠图、虚拟试衣、电商商品替换、图片片超清与修复、AI证件照生成、万物消除、专业人像美颜，以及AI动作迁移舞蹈视频。您的全能创意助手，让灵感触手可及。

Play audio/video locally on the host

根据描述，使用Mermaid、PlantUML或ASCII生成架构图、流程图、时序图和数据模型图。

通过 Runware API 生成图像与视频，支持 FLUX、Stable Diffusion、Kling AI 等主流模型。具备文生图、图生图、放大、文生视频及图生视频功能。适用于生成图像、基于提示词或图像创作视频、图像放大及 AI 图像变换。

用于在 Ardot 中把多个已有画板自动编排成可交付的衍生展示区。适合多状态对照、设计评审看板、流程演示、角色/设备矩阵。也可作为 CodeBuddy + Ardot AI 设计工作流的收尾节点，将 AI 生成的零散画板自动整理成结构化展示区并输出可分享链接。

Control whole-house music scenes combining Spotify playback with Airfoil speaker routing. Quick presets for morning, party, chill modes.

Search video dialogue and create reaction GIFs with timed subtitles. Perfect for creating meme-worthy clips from movies and TV shows.

强大的 yt‑dlp 命令行封装，可从 YouTube 及数千个其他网站下载视频、播放列表和音频，支持格式选择、质量控制、元数据嵌入以及 Cookie 认证。

使用 OpenAI Whisper 将音频文件转录为文本。支持自动语言检测，提供 txt、srt、vtt、json 等多种输出格式，支持批量处理和模型选择（tiny 到 large）。适用于音频录音、播客、语音消息、讲座、会议及任意音视频转写。支持 mp3、wav、m4a、ogg、flac、webm、opus、aac 格式。

Generate diverse creative illustrations via OpenAI Images API. Create book illustrations, editorial art, children's book art, concept illustrations, and artistic scenes. Use when user needs creative visual content for stories, articles, presentations, or artistic projects (e.g., "illustrate a fairy tale scene", "create editorial art about technology", "design children's book illustrations", "generate concept art for a story").

前端 UI 界面设计。当用户要创建网页、landing page、dashboard、React/Vue 组件、前端页面时触发。 输出 HTML/CSS/JS 代码。不适用于：静态图片设计（用 canvas-design）、公众号配图（用 weixin-canvas-design）。

Seedance 2.0 AI 视频生成，基于 EvoLink API，提供三种模式：文字→视频、图像→视频（1‑2 张图像）以及参考→视频（图像+视频+音频）。自动……

Local speech-to-text with NVIDIA Parakeet TDT 0.6B v3 (ONNX on CPU). 30x faster than Whisper, 25 languages, auto-detection, OpenAI-compatible API. Use when transcribing audio files, converting speech to text, or processing voice recordings locally without cloud APIs.

Design specific, quick-win lead magnets that attract qualified prospects, capture emails, and smoothly convert them into paying customers.

Control AirPlay speakers via Airfoil from the command line. Connect, disconnect, set volume, and manage multi-room audio with simple CLI commands.

使用 Reve AI API 生成、编辑、混合图像。适用于文本提示生成图像、按指令编辑图像或合并多个参考图像。需要 REVE_API_KEY 或 REVE_AI_API_KEY 环境变量。

Local STT and TTS on macOS using native Apple capabilities. Speech-to-text via yap (Apple Speech.framework), text-to-speech via say + ffmpeg. Fully offline, no API keys required. Includes voice quality detection and smart voice selection.